jondurbin commited on
Commit
58b1ced
1 Parent(s): e11fe41

Upload folder using huggingface_hub

Browse files
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e8a4ba94146791f9130a84f8c7be65a76c9a18d49b3daf1d4fcd1ae1a8da98
3
  size 11073631630
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f020071a60fdabf92ced598369403ba67528f1a2ff6a9e97d177d6f0b2c74d
3
  size 11073631630
special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "unk_token": {
24
  "content": "</s>",
25
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "</s>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -203,11 +203,11 @@
203
  }
204
  },
205
  "bos_token": "<s>",
 
206
  "clean_up_tokenization_spaces": true,
207
  "eos_token": "</s>",
208
  "model_max_length": 1000000000000000019884624838656,
209
  "pad_token": "</s>",
210
  "tokenizer_class": "GPTNeoXTokenizer",
211
- "unk_token": "</s>",
212
- "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}"
213
  }
 
203
  }
204
  },
205
  "bos_token": "<s>",
206
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
207
  "clean_up_tokenization_spaces": true,
208
  "eos_token": "</s>",
209
  "model_max_length": 1000000000000000019884624838656,
210
  "pad_token": "</s>",
211
  "tokenizer_class": "GPTNeoXTokenizer",
212
+ "unk_token": "</s>"
 
213
  }